smalltokgrab.py

#!/bin/env python3

from argparse import ArgumentParser
import os
from urllib.parse import parse_qsl, urlparse
import requests
from random import randint

HEADERS = {
    'Connection': 'keep-alive',
    'Pragma': 'no-cache',
    'Cache-Control': 'no-cache',
    'DNT': '1',
    'User-Agent': 'Mozilla/999.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36',
    'Accept': '*/*',
    'Sec-Fetch-Site': 'same-site',
    'Sec-Fetch-Mode': 'no-cors',
    'Sec-Fetch-Dest': 'video',
    'Referer': 'https://www.tiktok.com/',
    'Accept-Language': 'en-US,en;q=0.9,bs;q=0.8,sr;q=0.7,hr;q=0.6',
    'sec-gpc': '1',
    'Range': 'bytes=0-',
}

def tiktok_html_text(url, cookies):
    response = requests.get(url, cookies=cookies, headers=HEADERS)
    return response.text


def get_video_url(webpage_minimized_html):
    # simply returns the location of the video file on tiktoks cdn
    return webpage_minimized_html.split('"playAddr":"')[1].split('"')[0].replace(r'\u0026', '&').replace(r'\u002F', '/')


def download(cdn_url, cookies, out_path):
    '''
    downloads the video file from the tiktok cdn
    '''

    url = urlparse(cdn_url)

    params = tuple(parse_qsl(url.query))
    request = requests.Request(method='GET', url=f'{url.scheme}://{url.netloc}{url.path}', cookies=cookies, headers=HEADERS, params=params)

    prepared_request = request.prepare()
    session = requests.Session()
    response = session.send(request=prepared_request)
    response.raise_for_status()

    with open(os.path.abspath(out_path), 'wb') as output_file:
        output_file.write(response.content)


if __name__ == "__main__":
    parser = ArgumentParser()
    parser.add_argument('url', nargs='*', help='Video url (https://www.tiktok.com/@username/video/1234567890123456789).')
    args = parser.parse_args()
    
    web_id = str(randint(10**10, 10**11 - 1))
    cookies = {'tt_webid': web_id,'tt_webid_v2': web_id}
    
    for url in args.url:
        webpage_minimized_html = tiktok_html_text(url, cookies)
        cdn_url = get_video_url(webpage_minimized_html)

        user, vidID = url.replace('/video/', '/').split('?')[0].split('@')[1].split('/')
        out_path = f'{vidID} {user}.mp4'

        print(f'downloading:  "{url}"')
        print(f'output:       "{out_path}"')
        print()
        print(f'cdn-url:      "{cdn_url}"')
        print('---')

        download(cdn_url, cookies, out_path)